All of lore.kernel.org
 help / color / mirror / Atom feed
From: "D.Wythe" <alibuda@linux.alibaba.com>
To: kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com
Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org,
	linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org
Subject: [PATCH net-next v6 5/7] net/smc: use read semaphores to reduce unnecessary blocking in smc_buf_create() & smcr_buf_unuse()
Date: Sat, 26 Nov 2022 17:03:40 +0800	[thread overview]
Message-ID: <1669453422-38152-6-git-send-email-alibuda@linux.alibaba.com> (raw)
In-Reply-To: <1669453422-38152-1-git-send-email-alibuda@linux.alibaba.com>

From: "D. Wythe" <alibuda@linux.alibaba.com>

Following is part of Off-CPU graph during frequent SMC-R short-lived
processing:

process_one_work				(51.19%)
smc_close_passive_work			(28.36%)
	smcr_buf_unuse				(28.34%)
	rwsem_down_write_slowpath		(28.22%)

smc_listen_work				(22.83%)
	smc_clc_wait_msg			(1.84%)
	smc_buf_create				(20.45%)
		smcr_buf_map_usable_links
		rwsem_down_write_slowpath	(20.43%)
	smcr_lgr_reg_rmbs			(0.53%)
		rwsem_down_write_slowpath	(0.43%)
		smc_llc_do_confirm_rkey		(0.08%)

We can clearly see that during the connection establishment time,
waiting time of connections is not on IO, but on llc_conf_mutex.

What is more important, the core critical area (smcr_buf_unuse() &
smc_buf_create()) only perfroms read semantics on links, we can
easily replace it with read semaphore.

Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
 net/smc/smc_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index b571297..2f261c3 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1385,10 +1385,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
 		rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
 		if (!rc) {
 			/* protect against smc_llc_cli_rkey_exchange() */
-			down_write(&lgr->llc_conf_mutex);
+			down_read(&lgr->llc_conf_mutex);
 			smc_llc_do_delete_rkey(lgr, buf_desc);
 			buf_desc->is_conf_rkey = false;
-			up_write(&lgr->llc_conf_mutex);
+			up_read(&lgr->llc_conf_mutex);
 			smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
 		}
 	}
@@ -2650,7 +2650,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
 	int i, rc = 0, cnt = 0;
 
 	/* protect against parallel link reconfiguration */
-	down_write(&lgr->llc_conf_mutex);
+	down_read(&lgr->llc_conf_mutex);
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 		struct smc_link *lnk = &lgr->lnk[i];
 
@@ -2663,7 +2663,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
 		cnt++;
 	}
 out:
-	up_write(&lgr->llc_conf_mutex);
+	up_read(&lgr->llc_conf_mutex);
 	if (!rc && !cnt)
 		rc = -EINVAL;
 	return rc;
-- 
1.8.3.1


  parent reply	other threads:[~2022-11-26  9:04 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-26  9:03 [PATCH net-next v6 0/7] optimize the parallelism of SMC-R connections D.Wythe
2022-11-26  9:03 ` [PATCH net-next v6 1/7] net/smc: remove locks smc_client_lgr_pending and smc_server_lgr_pending D.Wythe
2023-01-29 15:11   ` D. Wythe
2023-01-30  8:37     ` Wenjia Zhang
2023-01-30 10:51       ` D. Wythe
2023-01-30 21:10         ` Wenjia Zhang
2023-01-31  3:06           ` D. Wythe
2022-11-26  9:03 ` [PATCH net-next v6 2/7] net/smc: allow confirm/delete rkey response deliver multiplex D.Wythe
2022-11-26  9:03 ` [PATCH net-next v6 3/7] net/smc: make SMC_LLC_FLOW_RKEY run concurrently D.Wythe
2022-11-26  9:03 ` [PATCH net-next v6 4/7] net/smc: llc_conf_mutex refactor, replace it with rw_semaphore D.Wythe
2022-11-26  9:03 ` D.Wythe [this message]
2022-11-26  9:03 ` [PATCH net-next v6 6/7] net/smc: reduce unnecessary blocking in smcr_lgr_reg_rmbs() D.Wythe
2022-11-26  9:03 ` [PATCH net-next v6 7/7] net/smc: replace mutex rmbs_lock and sndbufs_lock with rw_semaphore D.Wythe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1669453422-38152-6-git-send-email-alibuda@linux.alibaba.com \
    --to=alibuda@linux.alibaba.com \
    --cc=davem@davemloft.net \
    --cc=jaka@linux.ibm.com \
    --cc=kgraul@linux.ibm.com \
    --cc=kuba@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=wenjia@linux.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.